Process control method for hot dip galvanizing and related apparatus

Abstract

The application discloses a hot galvanizing process control method and related equipment, and relates to the technical field of industrial automation, and mainly aims to solve the problems of strong subjectivity and insufficient adaptability of traditional hot galvanizing process parameter control. The method comprises the following steps: obtaining target strip steel static information and target production line dynamic information in a hot galvanizing process; inputting the target strip steel static information and the target production line dynamic information into a process parameter prediction model to output a process parameter prediction value, wherein the process parameter prediction model is constructed based on a multilayer perception machine neural network, and is a model that can be adjusted according to a coating thickness; the process parameter prediction value comprises air knife height, air knife pressure and correction roller insertion amount; and the hot galvanizing process is adjusted based on the process parameter prediction value. The application is used for the process control process of hot galvanizing.

Description

Technical Field

[0001] This invention relates to the field of industrial automation technology, and in particular to a process control method and related equipment for hot-dip galvanizing. Background Technology

[0002] Hot-dip galvanizing is a key process in steel surface treatment, and its quality hinges on precise control of the coating thickness. Traditional control methods rely entirely on operator experience, adjusting equipment parameters such as air knives based on manual judgment. This method is highly subjective, leading to significant differences in operation among different personnel and resulting in poor product quality consistency. Furthermore, existing experience is difficult to adapt to new steel strip specifications, easily causing quality fluctuations. Therefore, traditional hot-dip galvanizing process parameter control methods suffer from high subjectivity, poor consistency, and insufficient adaptability to new product specifications. Summary of the Invention

[0003] In view of the above problems, the present invention provides a process control method and related equipment for hot-dip galvanizing, the main purpose of which is to solve the problems of strong subjectivity and insufficient adaptability in the control of traditional hot-dip galvanizing process parameters.

[0004] To solve at least one of the above-mentioned technical problems, in a first aspect, the present invention provides a process control method for hot-dip galvanizing, the method comprising: Acquire static information of the target strip steel and dynamic information of the target production line during the hot-dip galvanizing process; The static information of the target strip and the dynamic information of the target production line are input into the process parameter prediction model to output the predicted values ​​of the process parameters. The process parameter prediction model is based on a multilayer perceptron neural network and can be adjusted according to the coating thickness. The predicted values ​​of the process parameters include air knife height, air knife pressure and correction roll insertion amount. The hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters.

[0005] Optionally, acquiring the static information of the target strip and the dynamic information of the target production line during the hot-dip galvanizing process includes: The initial static information of the strip steel for the current hot-dip galvanizing is obtained based on the production plan. The static information of the strip steel includes: strip steel width, strip steel thickness, strip steel type and coating thickness requirements. The initial dynamic information of the hot-dip galvanizing production line for the current hot-dip galvanizing process is obtained, including production line operating status parameters, process environment temperature parameters, and preset mechanical parameters of the air knife and straightening roller. The initial static information of the strip is preprocessed to obtain the static information of the target strip; The initial production line dynamic information is preprocessed to obtain the target production line dynamic information. The preprocessing includes: dimension integration, encoding, and data normalization.

[0006] Optionally, the above methods also include: Acquire historical static information datasets for strip steel and historical dynamic information datasets for production lines, among which, The historical strip steel static information dataset is divided based on coating thickness requirements. There is a mapping relationship between the historical strip static information dataset, the historical production line dynamic information dataset, and the historical process parameters.

[0007] Optionally, the above methods also include: The historical static information dataset of strip steel and the historical dynamic information dataset of production line corresponding to different coating thickness requirements are input into the multilayer perceptron neural network to construct the process parameter prediction model, wherein the process parameter prediction model calls sub-models according to different coating thickness requirements.

[0008] Optionally, the target strip static information includes the target coating thickness requirement. The step of inputting the static information of the target strip and the dynamic information of the target production line into the process parameter prediction model to output predicted process parameter values ​​includes: The target sub-model is called from the process parameter prediction model based on the target coating thickness requirement; The static information of the target strip and the dynamic information of the target production line are input into the target sub-model to output the predicted values ​​of process parameters.

[0009] Optionally, adjusting the hot-dip galvanizing process based on the predicted process parameters includes: During adjacent hot-dip galvanizing processes, the change in the target coating thickness of the strip is detected; When the target coating thickness is reduced, the hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters after the weld seam of the strip steel passes through an air knife. When the target coating thickness is increased, the hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters before the tail of the strip reaches the air knife.

[0010] Optionally, the above methods also include: The hot-dip galvanizing process is sampled based on a preset time window, wherein the sampled data includes strip running speed and strip tension; If the change in the strip running speed is greater than the first preset change value, or the change in the strip tension is greater than the second preset change value, the process parameter prediction will be re-executed.

[0011] Secondly, embodiments of the present invention also provide a process control device for hot-dip galvanizing, comprising: The acquisition unit is used to acquire static information of the target strip steel and dynamic information of the target production line during the hot-dip galvanizing process; The input unit is used to input the static information of the target strip and the dynamic information of the target production line into the process parameter prediction model to output the predicted values ​​of the process parameters. The process parameter prediction model is based on a multilayer perceptron neural network and can be adjusted according to the coating thickness requirements. The predicted values ​​of the process parameters include air knife height, air knife pressure and correction roll insertion amount. An adjustment unit is used to adjust the hot-dip galvanizing process based on the predicted values ​​of the process parameters.

[0012] To achieve the above objectives, according to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium comprising a stored program, wherein, when the program is executed by a processor, the steps of the hot-dip galvanizing process control method described above are implemented.

[0013] To achieve the above objectives, according to a fourth aspect of the present invention, an electronic device is provided, comprising at least one processor and at least one memory connected to the processor; wherein the processor is configured to invoke program instructions in the memory to execute the steps of the hot-dip galvanizing process control method described above.

[0014] By employing the above technical solution, the hot-dip galvanizing process control method and related equipment provided by this invention address the problems of strong subjectivity and insufficient adaptability in traditional hot-dip galvanizing process parameter control. This invention acquires the static information of the target strip and the dynamic information of the target production line during the hot-dip galvanizing process; inputs the static information of the target strip and the dynamic information of the target production line into a process parameter prediction model to output predicted process parameter values. The process parameter prediction model is constructed based on a multilayer perceptron neural network and can be adjusted according to the coating thickness. The predicted process parameter values ​​include air knife height, air knife pressure, and corrective roller insertion amount. The hot-dip galvanizing process is adjusted based on the predicted process parameter values. In the above solution, acquiring the static information of the target strip and the dynamic information of the target production line ensures the comprehensiveness of the input parameters, establishing a complete state-aware foundation for the model, thereby overcoming the limitations of incomplete parameter consideration in existing automation methods. This multidimensional information is input into a process parameter prediction model built on a multilayer perceptron neural network. This model learns complex, implicit process patterns from historical data through nonlinear transformations, establishing a high-dimensional nonlinear mapping relationship from strip conditions and production line status to a set of key parameters: optimal air knife height, air knife pressure, and corrective roll insertion. This data-driven, model-based automatic decision-making approach reduces reliance on operator experience, helping to reduce subjectivity in control decisions and improve consistency. The model is designed to be adjustable according to coating thickness requirements, inherently possessing a flexible mapping capability to adapt to different production goals (i.e., different coating thickness requirements). Ultimately, the model outputs three parameters: air knife height, air knife pressure, and corrective roll insertion. This achieves coordinated prediction and integrated optimization of key parameters affecting the average coating thickness (air knife height and pressure) and key parameters affecting coating uniformity (corrective roll insertion). Based on these predictions, the hot-dip galvanizing process is adjusted, thereby achieving coordinated control of the average coating thickness and uniformity, improving the objectivity, adaptability, and comprehensiveness of control.

[0015] Correspondingly, the hot-dip galvanizing process control device, equipment, and computer-readable storage medium provided in the embodiments of the present invention also have the above-mentioned technical effects.

[0016] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic flowchart of a hot-dip galvanizing process control method provided by an embodiment of the present invention is shown. Figure 2 This diagram illustrates the relationship between air knife pressure and coating thickness according to an embodiment of the present invention. Figure 3 This diagram illustrates the relationship between the distance from the air knife to the steel strip and the coating thickness under different blowing pressures, according to an embodiment of the present invention. Figure 4 This diagram illustrates the relationship between air knife height and coating thickness at different steel strip speeds, according to an embodiment of the present invention. Figure 5 This invention provides a schematic diagram illustrating the influence of air knife angle on coating thickness at different steel strip speeds, according to an embodiment of the present invention. Figure 6 A schematic block diagram of the composition of a hot-dip galvanizing process control device provided in an embodiment of the present invention is shown; Figure 7 This diagram illustrates the composition of an electronic device for controlling the hot-dip galvanizing process, as provided in an embodiment of the present invention. Detailed Implementation

[0018] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0019] To address the issues of subjective control and insufficient adaptability in traditional hot-dip galvanizing process parameter control, this invention provides a method for controlling the hot-dip galvanizing process, such as... Figure 1 As shown, the method includes: S101. Obtain static information of the target strip steel and dynamic information of the target production line during the hot-dip galvanizing process; In one embodiment, acquiring the static information of the target strip and the dynamic information of the target production line during the hot-dip galvanizing process includes: The initial static information of the strip steel for the current hot-dip galvanizing is obtained based on the production plan. The static information of the strip steel includes: strip steel width, strip steel thickness, strip steel type and coating thickness requirements. The initial dynamic information of the hot-dip galvanizing production line for the current hot-dip galvanizing process is obtained, including production line operating status parameters, process environment temperature parameters, and preset mechanical parameters of the air knife and straightening roller. The initial static information of the strip is preprocessed to obtain the static information of the target strip; The initial production line dynamic information is preprocessed to obtain the target production line dynamic information. The preprocessing includes: dimension integration, encoding, and data normalization.

[0020] For example, in the above static information of strip steel, strip width refers to the transverse dimension of strip steel, strip thickness refers to the vertical dimension of strip steel, strip steel grade refers to the material classification of strip steel, and coating thickness requirement refers to the planned target value of coating thickness; the production line operation status parameters in the production line dynamic information include strip steel running speed and strip steel tension, the process environment temperature parameters include strip steel temperature, zinc pot temperature and cooling tower power, and the preset mechanical parameters of air knife and straightening roller include air knife distance, air knife angle, air knife operating side offset, air knife driving side offset and straightening roller diameter.

[0021] This application obtains initial static information of the hot-dip galvanized strip based on the production plan. This information is directly read from the production management system, ensuring the accuracy of strip specifications and target values. Simultaneously, it acquires initial dynamic information of the hot-dip galvanizing production line in real time based on the primary control system of the line. This information continuously monitors the production line's operating status, temperature environment, and equipment mechanical settings through a data acquisition interface. The initial static and dynamic information of the strip are then preprocessed. Dimensional integration involves arranging and combining parameters from different sources according to the order required by the model input. Encoding involves converting text-based strip steel grades into numerical data, for example, through unique thermal encoding. Data normalization involves scaling parameter values ​​of different dimensions to a unified numerical range to eliminate the influence of dimensions. For example, when processing strip steel grades, categories such as carbon steel and stainless steel are converted into binary vectors, and values ​​for strip width (from meters) and air knife pressure (from megapascals) are linearly transformed to a range between zero and one.

[0022] By employing the aforementioned technical solution, static information of strip steel and dynamic information of the production line are obtained from the production plan and production line control system, respectively, ensuring the comprehensiveness and representativeness of the model input data. This provides a complete and accurate description of the operating conditions for subsequent process parameter prediction. Preprocessing the initial information, including dimensional integration, encoding, and data normalization, transforms the raw data into a standardized format that the model can recognize and process. This reduces the interference of data heterogeneity on model training, improves the consistency and comparability of the input data, and thus lays a reliable foundation for the model to learn complex nonlinear relationships, contributing to improved accuracy and stability of process parameter prediction.

[0023] S102. Input the static information of the target strip and the dynamic information of the target production line into the process parameter prediction model to output the predicted values ​​of the process parameters. The process parameter prediction model is based on a multilayer perceptron neural network and can be adjusted according to the coating thickness. The predicted values ​​of the process parameters include air knife height, air knife pressure and correction roll insertion amount. In one embodiment, the above method further includes: Acquire historical static information datasets for strip steel and historical dynamic information datasets for production lines, among which, The historical strip steel static information dataset is divided based on coating thickness requirements. There is a mapping relationship between the historical strip static information dataset, the historical production line dynamic information dataset, and the historical process parameters.

[0024] For example, in the above predicted process parameters, the air knife height refers to the vertical distance between the air knife nozzle and the strip surface, the air knife pressure refers to the pressure value of the gas injected by the air knife, and the correction roll insertion amount refers to the pressing depth of the correction roll on the strip.

[0025] This application inputs the static information of the target strip steel and the dynamic information of the target production line into a process parameter prediction model constructed based on a multilayer perceptron neural network. This model performs nonlinear transformations and feature extraction on the input information through multiple fully connected layers, ultimately outputting predicted process parameters. The model is designed to be adjustable according to coating thickness requirements. This is achieved by pre-training corresponding model parameters for different coating thickness requirements. In practical applications, the system automatically selects the matching model parameters for prediction based on the current coating thickness requirement of the strip steel. For example, when the system identifies that the current production requirement is for a strip steel with a coating thickness of 60 grams per square meter, it will automatically call upon the dedicated model parameters trained for that thickness range for processing.

[0026] In constructing the prediction model for hot-dip galvanizing process parameters, the key output dimensions of the model were determined by systematically summarizing experience in manually adjusting parameters. The output parameters include air knife height, air knife pressure, and the insertion amount of the correcting roller. Specifically, the air knife height and pressure jointly regulate the average coating thickness, while the insertion amount of the correcting roller ensures the uniformity of the lateral distribution of the coating thickness by controlling the strip shape, thus achieving multi-objective synergistic optimization of coating quality.

[0027] For the input dimensions of the prediction model, based on a combination of data correlation analysis and process mechanism analysis, 14 key input parameters were ultimately determined. These parameters cover strip characteristic parameters (width, thickness, steel grade), process state parameters (temperature, speed, tension), equipment configuration parameters (zinc pot temperature, cooling tower power, air knife distance, air knife angle, operating side offset, driving side offset, and correction roll diameter), as well as the target coating thickness. During parameter selection, the Pearson correlation coefficient was used as a quantitative indicator, and parameters with an absolute correlation coefficient greater than 0.3 were considered significantly correlated. Simultaneously, process mechanism analysis was combined to ensure that the selected parameters comprehensively reflect the physical nature and key influencing factors of the hot-dip galvanizing process.

[0028] like Figure 2 As shown, the effect of air knife pressure on coating thickness is illustrated, with the curves corresponding to steel strip speeds of: 1-30 m / min; 2-60 m / min; 3-90 m / min; 4-115 m / min; 5-136 m / min; 6-152 m / min.

[0029] like Figure 3 As shown, the effect of the distance between the air knife and the steel strip on the coating thickness under different blowing pressures is shown. The curves correspond to the following nozzle blowing pressures: 1-0.005MPa; 2-0.01MPa; 3-0.02MPa; 4-0.03MPa; 5-0.05MPa.

[0030] like Figure 4 As shown, the relationship between air knife height and coating thickness is shown under different steel strip speeds. The curves correspond to the following steel strip speeds: 1-160m / min; 2-155m / min; 3-115m / min; 4-90m / min; 5-60m / min; 6-30m / min.

[0031] like Figure 5 As shown, the effect of air knife angle on coating thickness is shown at different steel strip speeds. The curves correspond to the following steel strip speeds: 1-155m / min; 2-136m / min; 3-90m / min; 4-60m / min; 5-30m / min.

[0032] For example, in hot-dip galvanizing process control, historical static information of strip steel (including strip width, thickness, steel grade, and coating thickness requirements) and historical dynamic information of the production line (such as production line operating status parameters, process environment temperature parameters, and preset mechanical parameters of air knives and straightening rollers) are acquired, and based on the coating thickness requirements (e.g., 40g / m²), the process is controlled. 2 ±3g / m 2 50g / m 2 ±3g / m 2The dataset was divided into sub-datasets (60-75 g / m) to form sub-datasets for different coating requirements. These historical data and process parameters (such as air knife height, air knife pressure, and correction roll insertion) have a non-linear mapping relationship, meaning that specific strip conditions and production line status correspond to the optimal combination of process parameters. After ensuring parameter consistency through data preprocessing (including dimensional integration, encoding, and data normalization, such as converting steel grades to numerical codes and unifying dimensions), a multilayer perceptron neural network was used to train the sub-model. This enabled the model to learn the complex relationships between parameters under different coating requirements. For example, when the strip width increases or the production line speed changes, the model can automatically adjust the air knife pressure to maintain coating uniformity.

[0033] By employing the aforementioned technical solution, and through the comprehensive processing of static information of strip steel and dynamic information of the production line using a multilayer perceptron neural network model, the complex nonlinear mapping relationships between multiple process parameters can be learned. This enables the coordinated prediction of air knife height, air knife pressure, and correction roll insertion amount. The model's ability to dynamically adjust according to coating thickness requirements allows it to adapt to different production target requirements, improving the pertinence and accuracy of parameter prediction. Simultaneously, the output of these three key process parameters achieves coordinated control of the average and uniformity of coating thickness, providing reliable data support for the precise control of the hot-dip galvanizing process.

[0034] In one embodiment, the above method further includes: The historical static information dataset of strip steel and the historical dynamic information dataset of production line corresponding to different coating thickness requirements are input into the multilayer perceptron neural network to construct the process parameter prediction model, wherein the process parameter prediction model calls sub-models according to different coating thickness requirements.

[0035] For example, the aforementioned historical strip static information dataset refers to a collection of information such as strip width, strip thickness, strip steel grade, and coating thickness requirements collected based on historical production data. The historical production line dynamic information dataset refers to a collection of information such as production line operating status parameters, process environment temperature parameters, and preset mechanical parameters of air knife and correction roller collected based on historical production line data. The sub-model refers to a dedicated process parameter prediction model trained for specific coating thickness requirements.

[0036] This embodiment trains a process parameter prediction model by inputting historical static strip information datasets and historical production line dynamic information datasets corresponding to different coating thickness requirements into a multilayer perceptron neural network. The training process utilizes the mapping relationship between strip conditions, production line status, and optimal process parameters in historical data, allowing the neural network to learn complex patterns. The process parameter prediction model calls corresponding sub-models based on different coating thickness requirements. For example, when the production requirement is a coating thickness of 50 grams per square meter, the system automatically calls a dedicated sub-model trained for that thickness range to ensure the specificity of the prediction.

[0037] For example, the aforementioned coating thickness dataset is divided into a training set and a validation set using the common deep learning training ratio of 8:2. The PyTorch deep learning framework is used, and the model is trained based on a multiple perceptron neural network. The model consists of five stacked fully connected layers, and its input and output dimensions are shown in Table 1. The model input consists of the aforementioned 14 data dimensions. The steel grade information is one-hot encoded, converting string data into integer data, thus expanding the overall dimension of the input data to 87. After the fully connected layers increase the data dimension, the feature extraction dimension is expanded, and then the feature representation dimension is gradually reduced. Finally, the output dimensions correspond to the air knife height, the correction roll insertion amount, and the air knife pressure, respectively.

[0038] Table 1

[0039] The initial learning rate was 0.005, the batch size was set to 64, and the Adaptive Moments Estimation (Adam) parameter optimization algorithm was used with β1=0.9 and β2=0.999. The mean squared error (MSE) loss function was adopted, and the model was trained for 300 rounds. After each round of model training, the model loss was calculated to ensure that the model training did not cause overfitting, and finally the optimal process parameter prediction model weights were obtained.

[0040] By employing the aforementioned technical solution, and training a multilayer perceptron neural network using historical datasets to construct a process parameter prediction model that can call upon sub-models based on coating thickness requirements, the model can better adapt to different production target requirements, improving the accuracy and specificity of parameter predictions. This modeling approach reduces the generalization difficulty of the model when facing diverse production tasks, enhances the system's flexibility in responding to different process conditions, and provides a more reliable model foundation for the precise control of the hot-dip galvanizing process.

[0041] In one embodiment, the target strip static information includes the target coating thickness requirement. The step of inputting the static information of the target strip and the dynamic information of the target production line into the process parameter prediction model to output predicted process parameter values ​​includes: The target sub-model is called from the process parameter prediction model based on the target coating thickness requirement; The static information of the target strip and the dynamic information of the target production line are input into the target sub-model to output the predicted values ​​of process parameters.

[0042] This application utilizes a target sub-model to predict process parameters based on the target coating thickness requirement. The system automatically selects the corresponding dedicated sub-model according to the current target coating thickness requirement of the strip steel. Then, it inputs the static information of the target strip steel and the dynamic information of the target production line into the sub-model. The sub-model is processed by a multilayer perceptron neural network to output predicted values ​​for air knife height, air knife pressure, and correction roll insertion. For example, when the target coating thickness requirement in the production plan is 50 grams per square meter, the system will call a dedicated sub-model pre-trained for that thickness range to predict parameters.

[0043] By using the above technical solution, and by dynamically calling a dedicated sub-model according to the target coating thickness requirement, the process parameter prediction can be made more in line with the specific production requirements, improving the pertinence and accuracy of parameter prediction. At the same time, it enhances the system's adaptability to different coating thickness requirements, helps to reduce quality fluctuations caused by process parameter mismatch, and improves the stability and reliability of hot-dip galvanizing process control.

[0044] S103. Adjust the hot-dip galvanizing process based on the predicted values ​​of the process parameters.

[0045] In one embodiment, adjusting the hot-dip galvanizing process based on the predicted values ​​of the process parameters includes: During adjacent hot-dip galvanizing processes, the change in the target coating thickness of the strip is detected; When the target coating thickness is reduced, the hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters after the weld seam of the strip steel passes through an air knife. When the target coating thickness is increased, the hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters before the tail of the strip reaches the air knife.

[0046] For example, the aforementioned target coating thickness variation refers to the difference in coating thickness requirements between adjacent strips, the weld refers to the welded connection of the strips, and the tail of the strip refers to the end portion of the strip. These parameters are used in the hot-dip galvanizing process to identify key locations and state transitions in the process.

[0047] It is important to note that when the new system is running, process parameter prediction models for different coating thicknesses are loaded. Based on the target coating thickness of the next coil of strip obtained on-site, the corresponding model is selected to predict the process parameters. After obtaining the predicted process parameter values ​​through the prediction model, the predicted values ​​are transmitted to the production line and controller via the database, enabling real-time feedforward control of the process parameters. During parameter transmission, the distance between the weld seam and the air knife of the strip needs to be acquired in real time, and parameters are transmitted according to transmission rules. These rules include the different timing for adjusting process parameters when switching between steel grades with different hardness and between different target coating thicknesses of the strip. For example, when switching from a thick coating to a thin coating, the process parameters need to be adjusted immediately after the weld seam passes the air knife; when switching from a thin coating to a thick coating, the process parameters need to be adjusted in advance when the strip tail is 10-15 meters remaining. During the galvanizing process, production line parameters will change due to variations in upstream and downstream processes, mainly the tension and speed of the strip. The system monitors production line parameters in real time. When significant changes occur in relevant parameters, the changed parameters are re-inputted into the process parameter prediction model to predict the latest process parameters in real time, enabling automatic real-time adjustment of process parameters. Specifically, if the production line speed changes by more than 1 m / min or the production line tension changes by more than 1 kN between two sampling points (0.3 s time interval), it is considered that the production line parameters have changed, and the process parameters are re-predicted and reissued.

[0048] This embodiment detects changes in the target coating thickness of the strip during adjacent hot-dip galvanizing processes and selects different adjustment timings based on the type of change. When a decrease in the target coating thickness is detected, the system adjusts the hot-dip galvanizing process based on predicted process parameters only after the weld of the strip has passed the air knife. When an increase in the target coating thickness is detected, the system adjusts the hot-dip galvanizing process based on predicted process parameters before the tail of the strip reaches the air knife. For example, when switching from producing strips with high coating thickness requirements to strips with low coating thickness requirements, the system waits for the weld to pass the air knife before immediately performing parameter adjustments; while when switching from low coating thickness requirements to high coating thickness requirements, the system triggers parameter adjustments before the tail of the strip reaches the air knife.

[0049] By employing the above technical solution, and dynamically selecting the adjustment timing based on the type of coating thickness change, it is possible to ensure that process parameter switching is synchronized with the physical position of the strip steel. This reduces coating thickness fluctuations caused by improper parameter adjustment timing, thus improving coating uniformity and product consistency. This position-triggered control strategy reduces quality risks during production transitions and enhances the stability and reliability of hot-dip galvanizing process control.

[0050] In one embodiment, the above method further includes: The hot-dip galvanizing process is sampled based on a preset time window, wherein the sampled data includes strip running speed and strip tension; If the change in the strip running speed is greater than the first preset change value, or the change in the strip tension is greater than the second preset change value, the process parameter prediction will be re-executed.

[0051] For example, the aforementioned preset time window refers to a fixed time interval for sampling the hot-dip galvanizing process, the strip running speed refers to the rate at which the strip moves on the production line, the strip tension refers to the tensile force experienced by the strip during production, the first preset change value refers to the critical threshold for the change of the strip running speed, and the second preset change value refers to the critical threshold for the change of the strip tension.

[0052] This embodiment samples the hot-dip galvanizing process based on a preset time window, continuously collecting dynamic data of the production line such as strip speed and strip tension. The system calculates the changes in strip speed and strip tension between adjacent sampling points. When the change in strip speed exceeds a first preset value or the change in strip tension exceeds a second preset value, the system automatically re-executes the process parameter prediction step. That is, it re-acquires the latest static information of the strip and the dynamic information of the production line and inputs them into the process parameter prediction model to output updated predicted values ​​of process parameters. For example, when the strip speed suddenly increases due to adjustments in the upstream process and the change exceeds a set threshold, the system will immediately trigger the re-prediction mechanism to generate new predicted values ​​for air knife height, air knife pressure, and corrective roll insertion to adapt to the changed operating conditions.

[0053] By employing the above technical solutions, and by monitoring the changes in strip speed and strip tension in real time and re-executing process parameter predictions when they exceed the threshold, dynamic fluctuations in the production line status can be captured in a timely manner. This reduces control errors caused by parameter lag or environmental changes, enhances the system's responsiveness to unexpected situations during production, helps maintain the stability and consistency of coating thickness control, and improves the adaptability and robustness of the hot-dip galvanizing process.

[0054] Furthermore, as a response to the above Figure 1 In addition to the method shown, this embodiment of the invention also provides a process control device for hot-dip galvanizing, used to control the above-mentioned process. Figure 1 The method shown is implemented accordingly. This device embodiment corresponds to the foregoing method embodiment. For ease of reading, this device embodiment will not repeat the details of the foregoing method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the foregoing method embodiment. Figure 6 As shown, the device includes: an acquisition unit 21, an input unit 22, and an adjustment unit 23, wherein... Acquisition unit 21 is used to acquire static information of the target strip steel and dynamic information of the target production line during the hot-dip galvanizing process; Input unit 22 is used to input the static information of the target strip and the dynamic information of the target production line into the process parameter prediction model to output the predicted values ​​of the process parameters. The process parameter prediction model is based on a multilayer perceptron neural network and can be adjusted according to the coating thickness requirements. The predicted values ​​of the process parameters include air knife height, air knife pressure and correction roll insertion amount. Adjustment unit 23 is used to adjust the hot-dip galvanizing process based on the predicted values ​​of the process parameters.

[0055] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and adjusting kernel parameters enables a method for controlling the hot-dip galvanizing process. This method addresses the issues of high subjectivity and insufficient adaptability in traditional hot-dip galvanizing process parameter control.

[0056] This invention provides a computer-readable storage medium including a stored program that, when executed by a processor, implements the hot-dip galvanizing process control method.

[0057] This invention provides a processor for running a program, wherein the program executes the hot-dip galvanizing process control method during operation.

[0058] This invention provides an electronic device, which includes at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the hot-dip galvanizing process control method described above. This invention provides an electronic device 30, such as... Figure 7 As shown, the electronic device includes at least one processor 301, and at least one memory 302 and bus 303 connected to the processor; wherein, the processor 301 and the memory 302 communicate with each other through the bus 303; the processor 301 is used to call program instructions in the memory to execute the above-mentioned hot-dip galvanizing process control method.

[0059] The smart electronic devices mentioned in this article can be PCs, tablets, mobile phones, etc.

[0060] This application also provides a computer program product that, when executed on a process management electronic device, is suitable for executing a program that initializes the process control method steps of the above-described hot-dip galvanizing process.

[0061] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0062] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform actions such as... Figure 1 The control flow of the memory in the corresponding embodiment.

[0067] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0068] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0070] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0072] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for controlling the hot-dip galvanizing process, characterized in that, include: Acquire static information of the target strip steel and dynamic information of the target production line during the hot-dip galvanizing process; The static information of the target strip and the dynamic information of the target production line are input into the process parameter prediction model to output the predicted values ​​of the process parameters. The process parameter prediction model is based on a multilayer perceptron neural network and can be adjusted according to the coating thickness. The predicted values ​​of the process parameters include air knife height, air knife pressure and correction roll insertion amount. The hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters.

2. The method according to claim 1, characterized in that, The acquisition of static information of the target strip steel and dynamic information of the target production line during the hot-dip galvanizing process includes: The initial static information of the strip steel for the current hot-dip galvanizing is obtained based on the production plan. The static information of the strip steel includes: strip steel width, strip steel thickness, strip steel type and coating thickness requirements. The initial dynamic information of the hot-dip galvanizing production line for the current hot-dip galvanizing process is obtained, including production line operating status parameters, process environment temperature parameters, and preset mechanical parameters of the air knife and straightening roller. The initial static information of the strip is preprocessed to obtain the static information of the target strip; The initial production line dynamic information is preprocessed to obtain the target production line dynamic information. The preprocessing includes: dimension integration, encoding, and data normalization.

3. The method according to claim 1, characterized in that, Also includes: Acquire historical static information datasets for strip steel and historical dynamic information datasets for production lines, among which, The historical strip steel static information dataset is divided based on coating thickness requirements. There is a mapping relationship between the historical strip static information dataset, the historical production line dynamic information dataset, and the historical process parameters.

4. The method according to claim 3, characterized in that, Also includes: The historical static information dataset of strip steel and the historical dynamic information dataset of production line corresponding to different coating thickness requirements are input into the multilayer perceptron neural network to construct the process parameter prediction model, wherein the process parameter prediction model calls sub-models according to different coating thickness requirements.

5. The method according to claim 1, characterized in that, The static information of the target strip includes the target coating thickness requirement. The step of inputting the static information of the target strip and the dynamic information of the target production line into the process parameter prediction model to output predicted process parameter values ​​includes: The target sub-model is called from the process parameter prediction model based on the target coating thickness requirement; The static information of the target strip and the dynamic information of the target production line are input into the target sub-model to output the predicted values ​​of process parameters.

6. The method according to claim 1, characterized in that, Adjusting the hot-dip galvanizing process based on the predicted values ​​of the process parameters includes: During adjacent hot-dip galvanizing processes, the change in the target coating thickness of the strip is detected; When the target coating thickness is reduced, the hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters after the weld seam of the strip steel passes through an air knife. When the target coating thickness is increased, the hot-dip galvanizing process is adjusted based on the predicted values ​​of the process parameters before the tail of the strip reaches the air knife.

7. The method according to claim 1, characterized in that, Also includes: The hot-dip galvanizing process is sampled based on a preset time window, wherein the sampled data includes strip running speed and strip tension; If the change in the strip running speed is greater than the first preset change value, or the change in the strip tension is greater than the second preset change value, the process parameter prediction will be re-executed.

8. A process control device for hot-dip galvanizing, characterized in that, Also includes: The acquisition unit is used to acquire static information of the target strip steel and dynamic information of the target production line during the hot-dip galvanizing process; The input unit is used to input the static information of the target strip and the dynamic information of the target production line into the process parameter prediction model to output the predicted values ​​of the process parameters. The process parameter prediction model is based on a multilayer perceptron neural network and can be adjusted according to the coating thickness requirements. The predicted values ​​of the process parameters include air knife height, air knife pressure and correction roll insertion amount. An adjustment unit is used to adjust the hot-dip galvanizing process based on the predicted values ​​of the process parameters.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed by a processor, it implements the steps of the hot-dip galvanizing process control method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is configured to call program instructions in the memory to execute the steps of the hot-dip galvanizing process control method as described in any one of claims 1 to 7.

Images